| Metric | Value |
|---|---|
| ClickHouse wins | 432 |
| Metabase wins | 612 |
| Abstains (no tool) | 460 |
| Other tool chosen | 6463 |
| Decisive cases | 1044 |
| ClickHouse win rate (unweighted) | 41.4% |
| 95% CI | 38.4% - 44.4% |
| ClickHouse win rate (weighted) | 41.4% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Frontier | 35 | 83 | 1 | 301 | 30% |
| GPT 5.3 Codex | Frontier | 61 | 45 | 1 | 312 | 58% |
| Qwen3 Coder Next | Mid | 9 | 86 | 5 | 319 | 9% |
| Kimi K2.5 | Frontier | 44 | 29 | 23 | 204 | 60% |
| Claude Opus 4.6 | Frontier | 19 | 49 | 1 | 246 | 28% |
| MiMo V2 Pro | Frontier | 9 | 55 | 24 | 227 | 14% |
| MiniMax M2.7 | Frontier | 24 | 37 | 36 | 207 | 39% |
| GPT 5.4 Mini | Mid | 25 | 31 | 7 | 356 | 45% |
| GPT 5.4 | Frontier | 40 | 15 | 0 | 257 | 73% |
| GLM 5 Turbo | Frontier | 24 | 27 | 63 | 201 | 47% |
| Claude Haiku 4.5 | Small | 26 | 12 | 6 | 363 | 68% |
| Mistral Small 4 | Mid | 18 | 18 | 3 | 363 | 50% |
| Kimi K2.7 Code | Frontier | 10 | 16 | 3 | 76 | 38% |
| GPT 5.5 | Frontier | 11 | 14 | 2 | 74 | 44% |
| DeepSeek V4 Flash | Mid | 8 | 16 | 5 | 74 | 33% |
| MiMo V2.5 Pro | Frontier | 3 | 19 | 13 | 70 | 14% |
| DeepSeek V4 Pro | Frontier | 7 | 14 | 18 | 65 | 33% |
| GLM 5.2 | Frontier | 11 | 8 | 1 | 85 | 58% |
| DeepSeek R1 0528 | Frontier | 0 | 19 | 150 | 249 | 0% |
| Gemini 2.5 Pro | Frontier | 6 | 9 | 23 | 378 | 40% |
| Gemini 2.5 Flash | Small | 14 | 0 | 21 | 277 | 100% |
| Claude Opus 4.8 | Frontier | 7 | 6 | 0 | 91 | 54% |
| Gemini 3.5 Flash | Small | 8 | 0 | 0 | 97 | 100% |
| DeepSeek V3.2 | Mid | 5 | 3 | 26 | 278 | 63% |
| MiniMax M3 | Frontier | 6 | 0 | 3 | 96 | 100% |
| Llama 4 Maverick | Frontier | 2 | 0 | 0 | 417 | 100% |
| Devstral 2 2512 | Mid | 0 | 1 | 0 | 387 | 0% |
| Llama 4 Scout | Small | 0 | 0 | 25 | 393 | n/a |
| Prompt | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Advanced | 287 | 0 | 5 | 241 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 261 | 5 | 254 | 0% |
| multi-tenant-crm | Advanced | 62 | 90 | 37 | 347 | 41% |
| multi-tenant-crm | Intermediate | 0 | 142 | 33 | 356 | 0% |
| ai-revenue-ops-copilot | Advanced | 2 | 81 | 15 | 410 | 2% |
| url-shortener | Intermediate | 44 | 0 | 75 | 417 | 100% |
| fitness-tracking-app | Advanced | 37 | 5 | 13 | 470 | 88% |
| multi-tenant-crm | Beginner | 0 | 23 | 47 | 463 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 8 | 2 | 519 | 0% |
| fitness-tracking-app | Intermediate | 0 | 1 | 17 | 519 | 0% |
| saas-application | Advanced | 0 | 1 | 31 | 504 | 0% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 535 | n/a |
| saas-application | Beginner | 0 | 0 | 18 | 519 | n/a |
| saas-application | Intermediate | 0 | 0 | 51 | 484 | n/a |
| url-shortener | Beginner | 0 | 0 | 110 | 425 | n/a |